CN110070222B - Evolution regulation and control method and system for low traffic emission - Google Patents
Evolution regulation and control method and system for low traffic emission Download PDFInfo
- Publication number
- CN110070222B CN110070222B CN201910312976.5A CN201910312976A CN110070222B CN 110070222 B CN110070222 B CN 110070222B CN 201910312976 A CN201910312976 A CN 201910312976A CN 110070222 B CN110070222 B CN 110070222B
- Authority
- CN
- China
- Prior art keywords
- virtual
- emission
- phase
- traffic
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims description 68
- MGWGWNFMUOTEHG-UHFFFAOYSA-N 4-(3,5-dimethylphenyl)-1,3-thiazol-2-amine Chemical compound CC1=CC(C)=CC(C=2N=C(N)SC=2)=C1 MGWGWNFMUOTEHG-UHFFFAOYSA-N 0.000 claims description 34
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 34
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 34
- JCXJVPUVTGWSNB-UHFFFAOYSA-N nitrogen dioxide Inorganic materials O=[N]=O JCXJVPUVTGWSNB-UHFFFAOYSA-N 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 claims description 20
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000011144 upstream manufacturing Methods 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 16
- 238000004088 simulation Methods 0.000 abstract description 5
- 230000003993 interaction Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000000819 phase cycle Methods 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010587 phase diagram Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an evolution regulation and control method and system for low traffic emission, which can be used for constructing virtual intersections corresponding to real intersections aiming at intersections with different geometric shapes and topological structures; the optimization of the signal control scheme with low traffic emission is realized based on a microscopic simulation platform, so that the risk caused by an unreasonable signal scheme is reduced; because the optimization of the evolution control scheme takes the average delay and the traffic emission of the vehicle as comprehensive indexes, the multi-objective optimization is realized, the average delay and the emission of the vehicle can be obviously reduced after multiple times of learning, and the traffic capacity of the intersection is improved. In addition, the system of the invention can learn the optimization control scheme of low traffic emission through interaction with the environment, thereby solving the problem of difficult accurate mathematical modeling and being better suitable for different intersections and traffic flow conditions.
Description
Technical Field
The invention relates to the technical field of road traffic control and ecological traffic, in particular to an evolution regulation and control method and system for low traffic emission.
Background
Urban road intersections are not only the bottleneck for traffic flow, but also the primary area for motor vehicle emissions. According to the statistics of environmental protection departments, the exhaust emission of motor vehicles is a main pollution source of urban atmospheric environment. Because the motor vehicle emission and the signal control scheme of the road intersection have close correlation, the research on the signal optimization control method for low traffic emission to reduce the vehicle distance delay and the tail gas emission at the intersection is of great significance.
The existing intersection optimization control method mainly aims to reduce the vehicle delay of the intersection when optimization timing is carried out according to an intersection delay model, and vehicle emission factors are not considered. In recent years, the research on traffic low-emission control has attracted attention, and certain achievements are obtained in the aspect of modeling the emission of single pollutants such as carbon monoxide, carbon dioxide, nitrogen dioxide and sulfur dioxide of a motor vehicle respectively, but the achievements are still based on a delay model (such as a Webster, HCM2000 delay model) and a parking number and queue length model derived from the delay model, and model parameters are difficult to calibrate; the method can not adapt to traffic flow conditions with different saturation; the differences between large, medium and small vehicles are not distinguished; and assume that the initial queue is zero.
The key point of the signal optimization control of the intersection traffic low emission is to establish a traffic control scheme-traffic emission-delay relation model. Due to the fact that influence factors are more, and a nonlinear strong coupling relation exists between the influence factors, accurate modeling is difficult, and therefore achieving intersection traffic low-emission optimization control is challenging.
Disclosure of Invention
The invention aims to provide an evolution regulation and control method and system for low traffic emission, which not only effectively reduce the average delay of vehicles at urban intersections, improve the traffic capacity of the intersections, but also reduce the pollution emission of carbon monoxide, nitrogen dioxide, sulfur dioxide and the like of the vehicles in the intersection areas, and solve the problem that the traffic control scheme-traffic emission-average delay at the intersections is difficult to model.
The purpose of the invention is realized by the following technical scheme:
an evolution regulation and control method for low emission of traffic comprises the following steps:
according to the geometric shape of an actual intersection, the channelizing of a road and the signal machine, a scene containing the corresponding virtual intersection and the virtual signal machine is constructed by adopting microscopic traffic simulation software, virtual vehicle detectors are arranged at an upstream entrance and an upstream exit of each road of the virtual intersection, and a specified number of large-sized, medium-sized and small-sized virtual vehicles are generated on each road;
setting each phase composed of non-conflict traffic flows according to the traffic flow direction of the virtual intersection;
acquiring the current queuing state of the road controlled by each phase according to the virtual vehicle detector;
obtaining optimal phase timing corresponding to the current queuing state of the road controlled by each phase according to a preset lookup table;
determining a phase execution sequence according to the current queuing length of the road controlled by each phase;
when the virtual signal machine sequentially executes the optimal phase timing of each phase according to the phase execution sequence, each virtual vehicle moves according to the microcosmic following model, the emission of each virtual vehicle is calculated by the microcosmic emission model, the average delay of the virtual vehicles at the virtual intersection in the current period and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide are obtained, the evaluation values in the lookup table are updated according to the average delay and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide, until each evaluation value is converged, and the evolution control of the low emission of the traffic at this time is completed.
According to the technical scheme provided by the invention, the virtual intersection corresponding to the real intersection can be constructed for the intersections with different geometric shapes and topological structures; the optimization of the signal control scheme with low traffic emission is realized based on a microscopic simulation platform, so that the risk caused by an unreasonable signal scheme is reduced; because the optimization of the evolution control scheme takes the average delay and the traffic emission of the vehicle as comprehensive indexes, the multi-objective optimization is realized, the average delay and the emission of the vehicle can be obviously reduced after multiple times of learning, and the traffic capacity of the intersection is improved. In addition, the system of the invention solves the problem of difficult accurate mathematical modeling by learning the optimization control scheme of low traffic emission through interaction with the environment, and is better suitable for different intersections and traffic flow conditions.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an evolution regulation and control method for low emission of traffic according to an embodiment of the present invention;
FIG. 2 is a phase diagram according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of an evolution regulation and control system for low emission of traffic according to a second embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a model-free traffic low-emission evolution control method, which carries out multi-objective optimization on low emission and average delay through microscopic traffic simulation, comprehensively considers factors influencing intersection vehicle delay and traffic emission, including traffic control schemes, vehicle idling, acceleration and deceleration, uniform motion behaviors, road canalization, geometric shapes, vehicle types and the like of intersections, better describes the complex relation between intersection signal schemes and vehicle average delay and traffic emission, and is suitable for the signal optimization control of low emission of traffic at different intersections.
Example one
As shown in fig. 1, a flow chart of an evolution regulation and control method for low emission of traffic provided by an embodiment of the present invention mainly includes the following steps:
and 11, according to the geometric shape of the real intersection, the channelizing of the road and the signal machine, adopting microscopic traffic simulation software to construct a scene containing the corresponding virtual intersection and the virtual signal machine, arranging virtual vehicle detectors at an upstream entrance and an upstream exit of each road of the virtual intersection, and generating a specified number of large-sized, medium-sized and small-sized virtual vehicles on each road.
Those skilled in the art will appreciate that the model size of the virtual vehicle may be defined in a conventional manner, such as by defining the metric as the size of the vehicle.
The embodiment of the invention is realized based on a simulation platform, and the conditions of different vehicles are considered for being consistent with the real traffic conditions. The different types of virtual vehicles may include the following settable parameters: desired speed, desired acceleration, minimum safe distance, following behavior, emission behavior; vehicle type (large, medium and small), vehicle geometry, speed, and maximum acceleration and deceleration performance.
In the embodiment of the invention, a traffic signal control scheme of a virtual intersection relates to the concepts of a lamp group, a signal group, a phase, a signal period and the like, wherein the lamp group is as follows: a complete vehicle red, yellow and green unit lamp or a combination of a pedestrian red and green unit lamp; the signal group is: a set of one or more signal light groups having the same light color sequence; the phase is as follows: simultaneously obtaining the display state of a signal group corresponding to one or more traffic flows of the right of way, wherein the phase green light time is the green light display time obtained by one phase; the signal period is as follows: the color of the signal light changes for a circle according to the set signal phase sequence.
The evolutionary design of the cross traffic signal control scheme can be expressed as: by designing the corresponding phase time length of each road traffic flow, the average delay of vehicles at the intersection is ensured, and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide is minimized.
And 12, setting each phase composed of non-conflict traffic flows according to the traffic flow direction of the virtual intersection.
Different requirements exist for the traffic flow of the area of the virtual intersection, and a plurality of possible conflict points are formed, wherein the conflict points are as follows: the intersection point of the driving tracks of two traffic flows in different directions in the virtual intersection;
in order to realize that the traffic flow of each road safely passes through the intersection area, different phases composed of non-conflict traffic flows are set to form a phase scheme. As shown in fig. 2, the phase set to be composed of non-conflicting traffic flows at least includes: the opposite traffic flow (1, 5) of the straight-going, the one-side straight-going and left-turning traffic flow (2, 3, 6, 7), and the left-turning and right-turning traffic flow (4, 8).
And step 13, acquiring the current queuing state of the road controlled by each phase according to the virtual vehicle detector.
The queuing state of the embodiment of the invention is mainly the length of the virtual vehicle queue; the current queuing state of the road controlled by each phase is represented as: s c ＝＜S c1 ,S c2 Wherein S c1 ＝＜S c11 ,S c12 ,S c13 ,S c14 >，S c2 ＝＜S c21 ,S c22 ,S c23 ,S c24 ＞，S c11 ～S c24 Indicating the current queuing state S c Virtual vehicle queue length of each road is contained, and the order state X = S c 。
In the embodiment of the invention, the virtual annunciator is controlled by a main control module, and the main control module generates a traffic signal control scheme according to an evolution control result of low traffic emission or utilizes a preset traffic signal control scheme at the initial time of evolution learning to carry out traffic signal timing on the virtual annunciator;
the traffic signal control scheme comprises reward indexes determined by the average delay of the virtual vehicles and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide; in particular, traffic signal control schemes may be represented by a quadruple: (S, A, P, R), wherein S i ＝＜S i1 ,S i2 Is a finite set of discrete, joined states, S i1 ～S i2 The sub-states are respectively corresponding to the vehicle queue length of each road entrance direction; a. The j ＝＜A j1 ,A j2 Is greater than corresponding queue length S i Green timing duration of phase, where A j1 ＝＜A j11 ,A j12 ,A j13 ,A j14 >And A j2 ＝＜A j21 ,A j22 ,A j23 ,A j24 Phases 1 to 8 shown in FIG. 2; p is a stateTransition probability (i.e. the probability that the queue length changes from one queue state to another after the virtual annunciator executes a phase green light timing scheme);
in the embodiment of the invention, the reward is calculated by the average delay of the virtual vehicle and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide, and the reward is higher when the average delay of the virtual vehicle and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide are smaller;
the calculation formula of the reward is as follows:
wherein, w 1 、w 2 Respectively representing the importance of the average delay and the average emission of vehicles at the virtual intersection, w 1 +w 2 =1; d represents the average delay of vehicles at the virtual intersection; e.g. of the type co 、co max Respectively representing the average carbon monoxide emission of the virtual vehicle and the maximum carbon monoxide in the atmosphere; e.g. of a cylinder no 、no max Respectively representing the average emission amount of nitrogen dioxide of the virtual vehicle and the maximum value of nitrogen dioxide in the atmosphere; e.g. of the type so 、so max Respectively representing the average emission of sulfur dioxide of a virtual vehicle and the maximum value of sulfur dioxide in the atmosphere.
And step 14, obtaining the optimal phase timing corresponding to the current queuing state of the road controlled by each phase according to a preset lookup table.
As shown in table 1, the predetermined look-up table includes: a queuing state set S (which can be 0 to the maximum queuing length) and a phase green light timing set A (which can be 0 to the maximum green light time) corresponding to the queuing state set; each subset in the queuing state set corresponds to the time length of a plurality of phase green light timing; the predetermined look-up table further comprises: and (3) setting an evaluation value set Q (S, A) when each subset in the queuing state set corresponds to each phase green light, wherein the evaluation value set can be set according to experience before the self-learning process is started.
TABLE 1 look-up table
| S | A | Q(S，A) |
When the current state X is not < 0,0 >, < 0,0 >, the phase green light timing set corresponding to the same queuing state as the state X is searched in the predetermined lookup table:
Selecting a phase green timing of the set of phase green timing such that the probability of state transition is maximized
When green lamps are matched as the optimum phase, o is N max Phase green light timing formulaOne of the schemes (or set {1,2, \8230;, N) max Any element of).
To avoid trapping partially optimal during evolution, actions such as simulated annealing for state X can be used
A random selection is performed.
And step 15, determining the phase execution sequence according to the size of the current queue length of the road controlled by each phase.
Obtaining the current queuing length of the road controlled by each phase, determining the execution sequence (i.e. phase sequence) of the phase shown in fig. 2 according to the queuing length from large to small, and in order to ensure that the green lighting timing time of the optimal phase is effective, the following steps are also required: if the phase corresponding to a certain road is in two continuous phases, and the green time of the optimal phase is smaller than the preset minimum green time, indicating that the road controlled by the current phase is not allocated with the green time;
if the sum of the optimal phase green light timing time of all the phases and the preset yellow light timing time is larger than the preset maximum cycle time, the phase green light timing is adjusted according to the proportion of the road flow controlled by each phase, and if the adjusted phase green light timing is smaller than the preset minimum phase green light timing, the adjustment is not carried out.
And step 16, sequentially executing the optimal phase timing of each phase by the virtual annunciator according to the phase execution sequence, enabling each virtual vehicle to move according to the micro-following model, calculating the emission of each virtual vehicle by the micro-emission model, obtaining the average delay of the virtual vehicles at the virtual intersection in the current period and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide, and updating the evaluation value in the lookup table according to the average delay and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide.
In an embodiment of the present invention, the movement of each virtual vehicle according to the microscopic following model includes: when the virtual vehicle runs on the road, determining the acceleration or deceleration at the next moment according to the speed of the front vehicle, the distance between the vehicles and the speed of the self vehicle;
in an embodiment of the present invention, the estimating, by the microscopic emission model, the emission amount of each virtual vehicle includes: and calling an emission model of the virtual vehicle according to the size of the model of the virtual vehicle, the speed, the deceleration, the acceleration and the idle speed of the virtual vehicle, and calculating the emission amount of carbon monoxide, nitrogen dioxide and sulfur dioxide.
In the embodiment of the present invention, the evaluation value in the lookup table may be updated by using the following formula:
wherein, the
Representing a set of possible green light timings at each phase of state X; the set Y represents the queuing state Y = < Y of the road controlled by each phase after the green light timing of the current optimal phase is executed 11 ,Y 12 ,Y 13 ,Y 14 ＞,<Y 21 ,Y 22 ,Y 23 ,Y 24 ＞＞；r j Is the corresponding reward R; γ is a preset discount factor (e.g., 0.96); alpha represents the learning rate, and is calculated according to the number m of times that the state X appears in the self-learning process, and is represented as
And step 17, repeating the steps 12 to 16 until each evaluation value Q (S, A) converges, and continuously updating the evaluation values through multiple evolutionary learning to obtain a more accurate lookup table so as to complete the low-emission evolutionary control of the traffic.
And after the evolution learning of the traffic signal control is finished, the evolution learning is sent to traffic signal control software, the traffic signal control software is transmitted to a real signal machine through a network, and the real signal machine calls and executes the evolution learning.
The embodiment of the invention can construct a virtual intersection corresponding to a real intersection aiming at intersections with different shapes, geometric dimensions and topological structures; the optimization of the signal control scheme with low traffic emission is realized on the basis of a simulation platform, so that the risk caused by an unreasonable signal scheme is reduced; in addition, vehicle emission and delay information can be accurately obtained, the average vehicle emission amount and delay can be remarkably reduced after evolution learning, and the traffic capacity of the intersection is improved.
Example two
Another embodiment of the present invention further provides an evolution regulation and control system for low emission of traffic, which is mainly used for implementing the method described in the first embodiment, as shown in fig. 3, the system mainly includes:
the virtual scene construction module 11 is used for constructing a scene containing a corresponding virtual intersection and a corresponding virtual annunciator by adopting microscopic traffic simulation software according to the geometric shape of the actual intersection, the road canalization and the annunciator;
a virtual signal machine 12, which is arranged at a preset position in the virtual scene and is used for generating a virtual traffic signal;
the virtual vehicle detector 14 is arranged at an upstream entrance and an upstream exit of each road of the virtual intersection, and is used for acquiring the current queuing state of the road controlled by each phase and calculating the average delay of the vehicles;
a departure module 13 for generating a designated number of large, medium and small virtual vehicles on each road;
the evolution control module 17 is used for setting each phase composed of non-conflict traffic flows according to the traffic flow direction of the virtual intersection and obtaining the optimal phase timing corresponding to the current queuing state of the road controlled by each phase according to a preset lookup table; determining a phase execution sequence according to the current queuing length of the road controlled by each phase; and sequentially executing the optimal phase timing of each phase by the virtual annunciator according to the phase execution sequence, enabling each virtual vehicle to move according to the microcosmic following model, calculating the emission of each virtual vehicle by the microcosmic emission model, obtaining the average delay of the virtual vehicles at the virtual intersection in the current period and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide, updating the evaluation values in the lookup table according to the average delay and the average emission of the carbon monoxide, the nitrogen dioxide and the sulfur dioxide, and finishing the evolution control of the low emission of the traffic at this time until each evaluation value is converged.
In the embodiment of the invention, the traffic flow of the virtual intersection area has different requirements, and a plurality of possible conflict points are formed, wherein the conflict points are as follows: the intersection point of the driving tracks of two traffic flows in different directions in the virtual intersection;
the set phase consisting of non-conflicting traffic flows comprises at least: the opposite traffic flow of straight running, the one-side straight running and left turning traffic flow, and the left turning and right turning traffic flow.
In the embodiment of the present invention, the system further includes: the main control module controls 18, and the main control module generates a traffic signal control scheme according to the evolution control result of the low traffic emission or utilizes a preset traffic signal control scheme to carry out traffic signal timing on the virtual signal machine 12;
the traffic signal control scheme comprises reward indexes determined by the average delay of the virtual vehicles and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide.
In the embodiment of the invention, the average delay of the virtual vehicle and the smaller the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide are, the higher the reward is;
the calculation formula of the reward is as follows:
wherein, w 1 、w 2 Respectively representing the importance of the average delay and the average emission of vehicles at the virtual intersection, w 1 +w 2 =1; d represents the average delay of vehicles at the virtual intersection; e.g. of the type co 、co max Respectively representing the average carbon monoxide emission of the virtual vehicle and the maximum carbon monoxide in the atmosphere; e.g. of the type no 、no max Respectively representing the average emission amount of nitrogen dioxide of the virtual vehicle and the maximum value of nitrogen dioxide in the atmosphere; e.g. of a cylinder so 、so max Respectively representing the average emission of sulfur dioxide of a virtual vehicle and the maximum value of sulfur dioxide in the atmosphere.
In the embodiment of the present invention, the system further includes:
the microscopic following behavior module 15 is realized by a microscopic following model and is used for determining the acceleration or deceleration at the next moment according to the speed of the front vehicle, the distance between the vehicles and the speed of the vehicle when each virtual vehicle runs on the road;
a microscopic emission behavior module 16, implemented by a microscopic emission model, for calculating the emission amount of each virtual vehicle: and calling an emission model of the virtual vehicle according to the size of the model of the virtual vehicle, the speed, the deceleration, the acceleration and the idle speed of the virtual vehicle, and calculating the emission amount of carbon monoxide, nitrogen dioxide and sulfur dioxide.
After the evolution learning of the signal control scheme with low traffic emission is completed by the modules in the embodiment of the invention, the main control module 18 sends the evolution learning result to the real signal 10 for execution through the traffic signal control software 19.
It should be noted that, specific implementation manners of functions implemented by the functional modules included in the system are described in detail in the foregoing embodiments, and therefore, detailed descriptions thereof are omitted here.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the system is divided into different functional modules to perform all or part of the above described functions.
Through the description of the above embodiments, it is clear to those skilled in the art that the above embodiments may be implemented by software, or by software plus a necessary general hardware platform. With this understanding, the technical solutions of the embodiments can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods according to the embodiments of the present invention.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (2)
1. An evolution regulation and control method for low traffic emission is characterized by comprising the following steps:
according to the geometric shape of an actual intersection, road canalization and signal machines, adopting microscopic traffic simulation software to construct a scene containing a corresponding virtual intersection and a corresponding virtual signal machine, arranging virtual vehicle detectors at an upstream entrance and an upstream exit of each road of the virtual intersection, and generating a specified number of large-sized, medium-sized and small-sized virtual vehicles on each road;
setting each phase composed of non-conflict traffic flows according to the traffic flow direction of the virtual intersection;
acquiring the current queuing state of the road controlled by each phase according to the virtual vehicle detector;
obtaining optimal phase timing corresponding to the current queuing state of the road controlled by each phase according to a preset lookup table;
determining a phase execution sequence according to the size of the current queuing length of the road controlled by each phase;
sequentially executing optimal phase timing of each phase by the virtual annunciator according to the phase execution sequence, enabling each virtual vehicle to move according to a microcosmic following model, calculating the emission of each virtual vehicle by the microcosmic emission model, obtaining the average delay of the virtual vehicles at the virtual intersection in the current period and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide, updating the evaluation values in the lookup table according to the average delay and the average emission of the carbon monoxide, the nitrogen dioxide and the sulfur dioxide, continuously updating the evaluation values through multiple evolutionary learning until each evaluation value is converged, and finishing the evolutionary control of the low emission of the traffic;
different requirements exist in the traffic flow of the virtual intersection area, a plurality of conflict points are formed, and the conflict points are as follows: the intersection point of the driving tracks of two traffic flows in different directions in the virtual intersection; the set phase consisting of non-conflicting traffic flows comprises at least: a phase consisting of a straight-going opposite traffic, a one-side straight-going and left-turning traffic, and a left-turning and right-turning traffic;
the virtual annunciator is controlled by a main control module, and the main control module generates a traffic signal control scheme according to an evolution control result of low traffic emission or utilizes a preset traffic signal control scheme at the initial time of evolution learning to carry out traffic signal timing on the virtual annunciator; the traffic signal control scheme comprises reward indexes determined by the average delay of the virtual vehicles and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide;
the average delay of the virtual vehicle and the smaller the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide are, the higher the reward is;
the calculation formula of the reward is as follows:
wherein, w 1 、w 2 Respectively representing the importance of the average delay and the average emission of vehicles at the virtual intersection, w 1 +w 2 =1; d represents the average delay of vehicles at the virtual intersection; e.g. of a cylinder co 、co max Respectively representing the average carbon monoxide emission of the virtual vehicle and the maximum carbon monoxide in the atmosphere; e.g. of the type no 、no max Respectively representing the average emission amount of nitrogen dioxide of the virtual vehicle and the maximum value of nitrogen dioxide in the atmosphere; e.g. of the type so 、so max Respectively representing the average emission of sulfur dioxide of the virtual vehicle and the maximum value of sulfur dioxide in the atmosphere;
the predetermined look-up table comprises: the system comprises a queuing state set X, a phase green light timing set A corresponding to the queuing state set, and an evaluation value set Q (X, A) corresponding to the queuing state set X and the phase green light timing set A, wherein the queuing state set X is 0-maximum queuing length, and the phase green light timing set A corresponding to the queuing state set is 0-maximum green light time;
the evaluation value in the lookup table is updated by the following formula:
wherein, the
Representing the set of green lighting timing at each phase of state X, the number of j being equal to the maximum number N of green lighting timing schemes at each phase max Determining, i.e., j ∈ {1,2, \8230;, N max }; the set Y represents the queuing state of the road controlled by each phase after the green light timing of the current optimal phase is executed; r is j Is the corresponding reward R; gamma is a preset discount factor; alpha represents the learning rate, calculated according to the number m of occurrences of the state X in the self-learning process, and is represented as
The virtual vehicles move according to the microcosmic following model and comprise the following steps: when the virtual vehicle runs on the road, determining the acceleration or deceleration at the next moment according to the speed of the front vehicle, the distance between the vehicles and the speed of the vehicle;
the estimation of the emission amount of each virtual vehicle by the microscopic emission model comprises the following steps: and calling an emission model of the virtual vehicle according to the size of the model of the virtual vehicle, the speed, the deceleration, the acceleration and the idle speed of the virtual vehicle, and calculating the emission amount of carbon monoxide, nitrogen dioxide and sulfur dioxide.
2. An evolutionary regulation system for low emissions in traffic, comprising:
the virtual scene construction module is used for constructing a scene containing a corresponding virtual intersection and a corresponding virtual annunciator by adopting microscopic traffic simulation software according to the geometric shape of the actual intersection, the road canalization and the annunciator;
the virtual signal machine is arranged at a preset position in the virtual scene and is used for generating a virtual traffic signal;
the virtual vehicle detector is arranged at an upstream entrance and an upstream exit of each road of the virtual intersection and is used for acquiring the current queuing state of the road controlled by each phase;
the departure module is used for generating a specified number of large, medium and small virtual vehicles on each road;
the evolution control module is used for setting each phase composed of non-conflict traffic flows according to the traffic flow direction of the virtual intersection and obtaining the optimal phase timing corresponding to the current queuing state of the road controlled by each phase according to a preset lookup table; determining a phase execution sequence according to the current queuing length of the road controlled by each phase; sequentially executing optimal phase timing of each phase by the virtual annunciator according to the phase execution sequence, enabling each virtual vehicle to move according to a microcosmic following model, calculating the emission of each virtual vehicle by the microcosmic emission model, obtaining the average delay of the virtual vehicles at the virtual intersection in the current period and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide, updating the evaluation values in the lookup table according to the average delay and the average emission of the carbon monoxide, the nitrogen dioxide and the sulfur dioxide, continuously updating the evaluation values through multiple evolutionary learning until each evaluation value is converged, and finishing the evolutionary control of the low emission of the traffic;
different requirements exist in the traffic flow of the virtual intersection area, a plurality of conflict points are formed, and the conflict points are as follows: the intersection point of the driving tracks of two traffic flows in different directions in the virtual intersection; the set phase consisting of non-conflicting traffic flows includes at least: the opposite traffic flow of straight running, the traffic flow of one side straight running and left turning, and the traffic flow of left turning and right turning;
the system further comprises: the master control module is used for generating a traffic signal control scheme according to an evolution control result of low traffic emission or utilizing a preset traffic signal control scheme at the initial time of evolution learning to carry out traffic signal timing on the virtual annunciator; the traffic signal control scheme comprises reward indexes determined by the average delay of the virtual vehicles and the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide;
the average delay of the virtual vehicle and the smaller the average emission of carbon monoxide, nitrogen dioxide and sulfur dioxide are, the higher the reward is;
the calculation formula of the reward is as follows:
wherein w 1 、w 2 Respectively representing the importance of the average delay and average emission of vehicles at the virtual intersection, w 1 +w 2 =1; d represents the average delay of vehicles at the virtual intersection; e.g. of the type co 、co max Respectively representing the average carbon monoxide emission of the virtual vehicle and the maximum carbon monoxide in the atmosphere; e.g. of the type no 、no max Respectively representing the average emission of nitrogen dioxide of the virtual vehicle and the maximum value of nitrogen dioxide in the atmosphere; e.g. of the type so 、so max Respectively representing the average emission of sulfur dioxide of the virtual vehicle and the maximum value of sulfur dioxide in the atmosphere;
the predetermined look-up table comprises: the system comprises a queuing state set X, a phase green light timing set A corresponding to the queuing state set, and an evaluation value set Q (X, A) corresponding to the queuing state set X and the phase green light timing set A, wherein the queuing state set X is 0-maximum queuing length, and the phase green light timing set A corresponding to the queuing state set is 0-maximum green light time;
the evaluation values in the lookup table are updated using the following formula:
wherein, the
Each phase green light configuration shown in state XThe number of j is determined by the maximum number N of green light timing schemes of each phase max Determining, i.e., j ∈ {1,2, \8230;, N max }; the set Y represents the queuing state of the road controlled by each phase after the green light timing of the current optimal phase is executed; r is j Is the corresponding reward R; gamma is a preset discount factor; alpha represents the learning rate, calculated according to the number m of occurrences of the state X in the self-learning process, and is represented as
The system further comprises:
the microcosmic following behavior module is realized by a microcosmic following model and is used for determining the acceleration or deceleration at the next moment according to the speed of the front vehicle, the distance between the vehicles and the speed of the vehicle when each virtual vehicle runs on the road;
and the microcosmic emission behavior module is realized by a microcosmic emission model and is used for calculating the emission of each virtual vehicle: and calling an emission model of the virtual vehicle according to the size of the model of the virtual vehicle, the speed, the deceleration, the acceleration and the idle speed of the virtual vehicle, and calculating the emission amount of carbon monoxide, nitrogen dioxide and sulfur dioxide.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910312976.5A CN110070222B (en) | 2019-04-18 | 2019-04-18 | Evolution regulation and control method and system for low traffic emission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910312976.5A CN110070222B (en) | 2019-04-18 | 2019-04-18 | Evolution regulation and control method and system for low traffic emission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070222A CN110070222A (en) | 2019-07-30 |
| CN110070222B true CN110070222B (en) | 2022-10-14 |
Family
ID=67368007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910312976.5A Active CN110070222B (en) | 2019-04-18 | 2019-04-18 | Evolution regulation and control method and system for low traffic emission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070222B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125862B (en) * | 2019-09-27 | 2023-12-26 | 长安大学 | Following model emission measuring and calculating method based on genetic algorithm and specific power |
| CN114333302B (en) * | 2021-12-15 | 2023-04-18 | 深圳先进技术研究院 | Global traffic optimization system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761883A (en) * | 2014-01-29 | 2014-04-30 | 中国科学技术大学 | Self-learning method and system for traffic signal control |
| CN105243855A (en) * | 2015-09-28 | 2016-01-13 | 大连理工大学 | Crossing signal timing optimization method for reducing exhaust gas emission of motor vehicle |
| CN106205123A (en) * | 2016-07-25 | 2016-12-07 | 大连理工大学 | A kind of reduction is delayed and the integrated main line intersection group time-space distribution collocation method of discharge |
| CN108734354A (en) * | 2018-05-23 | 2018-11-02 | 吉林大学 | A kind of urban road signalized intersections multiple target timing designing method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100309023A1 (en) * | 2009-06-05 | 2010-12-09 | Alexander Busch | Traffic Control System |
-
2019
- 2019-04-18 CN CN201910312976.5A patent/CN110070222B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761883A (en) * | 2014-01-29 | 2014-04-30 | 中国科学技术大学 | Self-learning method and system for traffic signal control |
| CN105243855A (en) * | 2015-09-28 | 2016-01-13 | 大连理工大学 | Crossing signal timing optimization method for reducing exhaust gas emission of motor vehicle |
| CN106205123A (en) * | 2016-07-25 | 2016-12-07 | 大连理工大学 | A kind of reduction is delayed and the integrated main line intersection group time-space distribution collocation method of discharge |
| CN108734354A (en) * | 2018-05-23 | 2018-11-02 | 吉林大学 | A kind of urban road signalized intersections multiple target timing designing method |
Non-Patent Citations (3)
| Title |
|---|
| 基于低碳交通的信号交叉口优化控制研究;王芳;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20150415;全文 * |
| 考虑低排放低延误的交通信号优化方法;杨兆升 等;《华南理工大学学报. 自然科学版》;20151031;第43卷(第10期);全文 * |
| 考虑排放特性的交通信号配时多目标优化研究;董文会;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20170315;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070222A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070222B (en) | Evolution regulation and control method and system for low traffic emission | |
| CN108734354B (en) | Multi-target timing optimization method for urban road signalized intersection | |
| Baker et al. | V2V communication based real-world velocity predictions for improved HEV fuel economy | |
| CN111856968B (en) | Large-scale traffic simulation system and method based on parallel computing | |
| He et al. | An adaptive variable neighborhood search ant colony algorithm for vehicle routing problem with soft time windows | |
| Deshpande et al. | In-vehicle test results for advanced propulsion and vehicle system controls using connected and automated vehicle information | |
| CN113415288A (en) | Sectional type longitudinal vehicle speed planning method, device, equipment and storage medium | |
| JP3520331B2 (en) | Traffic flow simulation device | |
| Kővári et al. | Reward design for intelligent intersection control to reduce emission | |
| Wu et al. | ES-CTC: A deep neuroevolution model for cooperative intelligent freeway traffic control | |
| CN113064423B (en) | Follow-up control model, method and system based on optimized transmission information | |
| CN108182812A (en) | Urban road intersection ecology driving behavior optimization method based on intensified learning | |
| CN115204455A (en) | Long-time-domain driving behavior decision method suitable for high-speed and loop traffic scene | |
| CN111238519B (en) | Multi-unmanned vehicle road finding method based on topological map and conflict elimination strategy | |
| Lamghari Elidrissi et al. | Modular design and adaptive control of urban signalized intersections systems using synchronized timed Petri nets | |
| CN109711054B (en) | Learning-based vehicle track generation method for vehicle communication | |
| CN114701517A (en) | Multi-target complex traffic scene automatic driving solution based on reinforcement learning | |
| Samizadeh et al. | Decision making for autonomous vehicles' strategy in triple-lane roundabout intersections | |
| CN109559527B (en) | Intersection signal timing method, storage medium and server | |
| Gupta | Look-ahead optimization of a connected and automated 48v mild-hybrid electric vehicle | |
| Xu et al. | A traffic-in-loop simulation system for validation of emission control strategy in diesel engine | |
| Fussey et al. | Optimisation of geofencing for mobility solutions in smart cities | |
| Anida et al. | Driving cycle analysis for fuel rate and emissions in Kuala Terengganu city during go-to-work time | |
| Chen et al. | Development and Testing of an Integrated Energy-Efficient Vehicle Speed and Traffic Signal Controller | |
| CN114036748A (en) | Method, equipment and medium for optimizing random simulation of circuit network signal control fusing safety consideration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |